cancel_vdi_task

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructive/write, but the description adds substantially more: the two-phase dry-run default, the exact contents of blast_radius (task type, state, progress), the refusal on unreadable task type/state, that applied work is not rolled back, and that the action is audited. This is rich behavioral context beyond the annotation set.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the write marker and the core action, then the dry-run/confirm split, then safety constraints. Every sentence earns its place, though the closing instruction about the user's prior request restates the blast-radius point already made.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description carries the return burden and does so by enumerating blast_radius fields. For a destructive, non-idempotent, open-world tool, it covers the prerequisites, refusal behavior, irreversibility, and audit trail an agent needs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents confirm and the other parameters, making 3 the baseline. The description still adds operational meaning beyond the terse schema text: what a bare call actually returns, that the default path mutates nothing, and the refusal condition tied to task_id resolvability.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Cancel a running pool task"), gives a concrete example (in-progress image push), and immediately distinguishes the dry-run read path from the actual cancel path. An agent can tell it apart from the sibling get_vdi_task_status, which only reads.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to cancel (confirm=True) versus when to stop at the blast radius, and names the alternative behavior. It even addresses the trap case of a user requesting the cancel before seeing the preview, telling the agent not to set confirm=True on that basis. Nothing is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.